Chika Okezie

Crazy goal: Building AI co from Nigeria w/ $0 funding. Not another chatbot. Creating AI sys that sim human behavior & make decisions across inds. 1st prod: AutoCare AI helps stranded drivers find mechanics via AI Digital Twins. Day 1. Building in public. Let's see where it goes.

A dataset with millions of records is useless if it can’t answer the questions your users are actually asking. Sometimes the most important progress isn’t building more features,it’s realizing you need to rebuild the foundation first.

The goal is no longer just to build an AI agent. The goal is to build an AI agent that can provide relevant recommendations based on where the user is located. My biggest takeaway from today is that successful AI systems are built around users, not datasets.

Day 3: Building in Public I’ll be documenting my wins, failures, bottlenecks, and the exact steps I take to solve them. If this is your first time seeing my posts, I hope my journey gives you a reason to stay.

@why_always_Neel Without that, it becomes difficult to build an accurate behavioral model of the user. The interesting challenge is combining real-time state, long-term memory, and behavior simulation into a feedback loop that continuously refines recommendations.

@why_always_Neel For memory, I’m leaning toward persistent semantic memory rather than thread-scoped state. The agent needs to learn long-term behavioral patterns, preferences, and historical outcomes to improve its simulations over time.

Currently at 55 followers Looking to connect with people interested in • Startups • AI • Engineering • hackathon • Systems • football If you’re building, learning, shipping, or just figuring things out let’s connect :)

If you are building ANY app, website, SaaS, AI tool or digital product used by people in Nigeria OR Europe, this can save you from massive fines in 2026. Exact compliance checklist for NDPA + GDPR: documents you MUST have, where they apply to your build, plus clear Do’s and Don’ts. Extremely practical for founders. Save & share!

@why_always_Neel A lot of people use the terms interchangeably, but they’re not the same thing. An LLM/AI workflow is a predefined sequence of steps defined by human AI Agent has a goal, not just a flow. Instead of following a fixed path, it decides which actions to take based on the situation

Knowledge Test: Do you know the difference between an LLM/AI workflow and an AI Agent?

@BraedendotTECH happy to connect. i'm building an AI Agent that simulates human behavior before generating a recommendation tailored to user current problem and preferences

looking to connect with more BUILDERS on here. if you’re into - Shipping projects - solving problems - design - building SaaS - vibe coding - AI tools - building in public - lost in life say Hi or drop what you’re working on looking to follow active ones 🫡

Instead of watching 2 hours of Fifa world cup tonight. watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how AI Agent and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into 30 core agentic engineering concepts every developer should actually know find it below ↓

@MoizArshi29 I’m building an AI Agent that simulates human behavior before giving out recommendations that aligns with individual preferences.

Founders Drop your startup below 👇 Tell us what you’re building in one sentence. Your next customer, investor, hire, or partner could be reading this right now.

The biggest lesson from today: AI projects don’t fail because of a lack of models. They fail because of poor data. The quality of your dataset often matters more than the sophistication of your AI. Today wasn’t about building an AI agent. It was about building the foundation.

Clean the data Not every record is useful. Some businesses may be closed, incomplete, or missing important details. Create a knowledge base Once the auto shop data is isolated and cleaned, it can become the foundation of the AI agent.

Today reminded me of something important about AI: Building the AI is not the hard part. Finding the data is. I started working on an AutoCare AI agent today and quickly realized I had a major bottleneck: